Download
1 variant available
fp16 SafeTensor
Biomechanicals_v2_lora1500.safetensors
Half precision, best balance • 36.11 MB
Verified: 3 years ago
14,7090 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(1,968)
Mar 17, 2023
Trained mostly on illustrations. Has the tendency to not produce real black, sometimes light leaks in from the corners, giving it an analog, scanned look.
Show more

1360 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
Trained on 100 images in biomechanical style. Mostly paintings and illustrations, a few photos of props and some renderings.
Try this prompt as a start:
"<lora:Biomechanicals_v2:0.7> style, hnsrdlf style, SUBJECT DESCRIPTION, intricate biomechanical detail"
I tried various models with this and got good results with: Analog Madness, Art & Eros, DreamShaper, ChilloutMix, Hassanblend1512, movieDiffusion, Elldreth's StolenDreams Mix, theAllysMix, LOFI, Timeless Diffusion and the original SD1.5 it is based on.
Note: some of the example images' prompts are from the img2img upscale, not the initial txt2img generation.

